yolo测试图片批量裁剪+pad指定尺寸

基于u版Yolo v3
detect_save_crop.py

import argparse
from sys import platform

from models import *  # set ONNX_EXPORT in models.py
from utils.datasets import *
from utils.utils import *


def detect(save_txt=True, save_img=False):
    img_size = (320, 192) if ONNX_EXPORT else opt.img_size  # (320, 192) or (416, 256) or (608, 352) for (height, width)
    out, source, weights, half, view_img = opt.output, opt.source, opt.weights, opt.half, opt.view_img
    webcam = source == '0' or source.startswith('rtsp') or source.startswith('http') or source.endswith('.txt')

    # Initialize
    device = torch_utils.select_device(device='cpu' if ONNX_EXPORT else opt.device)
    if os.path.exists(out):
        shutil.rmtree(out)  # delete output folder
    os.makedirs(out)  # make new output folder

    # Initialize model
    model = Darknet(opt.cfg, img_size)

    # Load weights
    attempt_download(weights)
    if weights.endswith('.pt'):  # pytorch format
        model.load_state_dict(torch.load(weights, map_location=device)['model'])
    else:  # darknet format
        _ = load_darknet_weights(model, weights)

    # Fuse Conv2d + BatchNorm2d layers
    # model.fuse()

    # Eval mode
    model.to(device).eval()

    # Export mode
    if ONNX_EXPORT:
        img = torch.zeros((1, 3) + img_size)  # (1, 3, 320, 192)
        torch.onnx.export(model, img, 'weights/export.onnx', verbose=True)
        return

    # Half precision
    half = half and device.type != 'cpu'  # half precision only supported on CUDA
    if half:
        model.half()

    # Set Dataloader
    vid_path, vid_writer = None, None
    if webcam:
        view_img = True
        torch.backends.cudnn.benchmark = True  # set True to speed up constant image size inference
        dataset = LoadStreams(source, img_size=img_size, half=half)
    else:
        save_img = True
        dataset = LoadImages(source, img_size=img_size, half=half)

    # Get classes and colors
    classes = load_classes(parse_data_cfg(opt.data)['names'])
    colors = [[random.randint(0, 255) for _ in range(3)] for _ in range(len(classes))]

    # Run inference
    t0 = time.